ModelCap
Current AI model comparison
Exact identities · public evidence
Microsoft
Fara1.5 9B
Position
#114
Index
40.9
Inherited
finetune of qwen/qwen3.5-9b · finetune (100%)
Comparison side 1
Qwen
Qwen3.5-9B
Position
#108
Index
42.1
Estimated
publisher-corpus-prior over 194 held-out anchors (33%); launch card against 3 resolved peers on 10 rows (67%); exceeds every named peer on 4 of 10 rows; optimism haircut 0.6 from cross-lab-probe; shrunk 3.9 up toward the measured corpus
Comparison side 2
Output / 1M
Unavailable
vs $0.15
Context
—
vs 262K
Weights
Open weights
vs Open weights